Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    . It

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이지만
    0.71
    社会主义
    0.69
    więks
    0.66
     innovators
    0.64
     automakers
    0.63
     epistem
    0.63
     enterprises
    0.60
     insanlar
    0.59
     doctrines
    0.59
     antihy
    0.59
    POSITIVE LOGITS
    a
    0.82
    т
    0.71
    ਾ
    0.70
    l
    0.66
    t
    0.63
    an
    0.62
     พร้อม
    0.62
     ソ
    0.61
     די
    0.60
    ط
    0.60
    Act Density 0.262%

    No Known Activations